Modeldex
Drag to turnCard front showing

MiniMaxTextCommon

MiniMax-M3

MiniMax multimodal model for long-context coding, perception, and agent planning

MiniMax-M3
Type
Text
Quality
75 · Top 25% on the Epoch Capabilities Index
Context window
1,000,000 tokens
Max output
512,000 tokens
Input price
$0.30 / 1M tokens
Output price
$1.20 / 1M tokens
Cache read
$0.06 / 1M tokens
Cache write
—
Parameters
427B (427,040,140,160)
Downloads
190K in the last 30 days
Likes
1.6K
Access to weights
Open download
Released
Jun 1, 2026
Knowledge cutoff
—
Takes in
Text, Image, Video
Puts out
Text
Reasoning
Yes
Tool calling
Yes
Structured output
No
File attachments
Yes
Access
Open weights
License
MiniMax Community license
Rarity
Common
Set number
913/1044
Open MiniMax docsWeights on Hugging FaceQuality 75Where to run it 61Evolution 5/5Race it 85 tok/sMeet its creatureBattle Solar Pro 4

License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 19, 2026. Official source: platform.minimax.io.

How good is it?

Public leaderboard scores for MiniMax-M3, refreshed daily from Epoch AI and LMArena.

Top 25% of the 277 models on the Epoch Capabilities Index: #70.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Benchmarks Epoch AI runs

Scores from Epoch AI and LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

56 providers sell MiniMax-M3 through an API, and 5 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

API providers

ProviderInputOutputContext
KenariFreeminimax-m3FreeFree1.05M
MiniMax Token Plan (minimax.cn)FreeMiniMax-M3FreeFree1.05M
MiniMax Token Plan (minimax.io)FreeMiniMax-M3FreeFree1.05M
NvidiaFreeminimaxai/minimax-m3FreeFree1M
SCNet Token PlanFreeMiniMax-M3FreeFree1.05M
Volcengine Ark Coding PlanFreeminimax-m3FreeFree1.05M
VultrCheapest paidminimax-m3$0.20$0.90524K
EmpirioLabs AIminimax-m3$0.23$0.901M
Ambientminimax/minimax-m3$0.23$0.96262K
CoreWeaveMiniMaxAI/MiniMax-M3$0.23$0.96262K
Show 46 more providers
ProviderInputOutputContext
NanoGPTminimax/minimax-m3$0.23$0.96512K
VancineMiniMax-M3$0.24$0.961.05M
Boundlessminimax-m3$0.28$1.101.05M
Deep InfraMiniMaxAI/MiniMax-M3$0.28$1.10524K
DevPass (LLM Gateway)minimax-m3$0.28$1.101.05M
Lilacminimaxai/minimax-m3$0.28$1.101.05M
LLM Gatewayconsensusprotocol/minimax-m3$0.28$1.101.05M
AIHubMixminimax-m3$0.29$1.151.05M
IteraComputeminimax/minimax-m3$0.30$1.191.05M
AbacusMiniMaxAI/MiniMax-M3$0.30$1.201M
ClinePasscline-pass/minimax-m3$0.30$1.201.05M
CommandCodeMiniMaxAI/MiniMax-M3$0.30$1.201M
Cortecsminimax-m3$0.30$1.201.05M
Eden AIminimax/MiniMax-M3$0.30$1.20524K
Fireworks AIaccounts/fireworks/models/minimax-m3$0.30$1.20512K
Incominimax-m3$0.30$1.201.05M
Jalapeno CloudMiniMax-M3$0.30$1.20524K
Kilo Gatewayminimax/minimax-m3$0.30$1.20524K
Merge Gatewayminimax/minimax-m3$0.30$1.201M
MiniMax (minimax.cn)MiniMax-M3$0.30$1.201M
MiniMax (minimax.io)OfficialMiniMax-M3$0.30$1.201M
Nebius Token FactoryMiniMaxAI/MiniMax-M3$0.30$1.201.05M
Novita AIminimax/minimax-m3$0.30$1.201M
OpenCodeminimax-m3$0.30$1.20512K
OpenCode Gominimax-m3$0.30$1.201M
OpenRouterminimax/minimax-m3$0.30$1.201.05M
OrcaRouterminimax/minimax-m3$0.30$1.201.05M
PioneerMiniMaxAI/MiniMax-M3$0.30$1.201M
Requestyminimax-m3$0.30$1.201M
SiliconFlowMiniMaxAI/MiniMax-M3$0.30$1.201.05M
Standard Computeminimax/minimax-m3$0.30$1.201.05M
Tempr Gatewayminimax/MiniMax-M3$0.30$1.201.05M
Together AIMiniMaxAI/MiniMax-M3$0.30$1.20524K
Vercel AI Gatewayminimax/minimax-m3$0.30$1.20512K
Synthetichf:MiniMaxAI/MiniMax-M3$0.60$1.20524K
Charm Hyperminimax-m3$0.33$1.31512K
CrossModelminimax/minimax-m3$0.33$1.321.02M
WaferMiniMax-M3$0.33$1.321.05M
TensorXminimax/minimax-m3$0.40$2.001.05M
GMI CloudMiniMaxAI/MiniMax-M3$0.60$2.401.05M
Ofoxminimax/minimax-m3$0.60$2.401.05M
Ollama Cloudminimax-m3$0.60$2.40512K
Opperminimax-m3$0.60$2.401M
SambaNovaMiniMax-M3$0.60$2.401.05M
ZenMuxminimax/minimax-m3$0.60$2.401.05M
302.AIMiniMax-M3$0.72$2.881.05M

Hugging Face Inference Providers

HostInputOutputContextSpeedFirst token
DeepInfraTools$0.28$1.10524K27 tok/s0.7s
FireworksFastestTools$0.30$1.20512K85 tok/s0.6s
NovitaTools$0.30$1.201M67 tok/s1.2s
Together AITools$0.30$1.20524K58 tok/s0.4s
Featherless—————

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.

More from MiniMax

MiniMax

MiniMax-M3.1-Flash

CTX1M
New
Reasoning · Vision · Tools
TextImageVideoInput$0.15/M
TextOutput$0.60/M

Frontier multimodal coding model with 1M context window and tunable thinking depth

Open weightsMIT1044/1044
MiniMax

MiniMax-Music3

SIZE2.4B
Text to speech
TextDownloads6.2K/mo
AudioLikes1.5K

Text-to-audio model from MiniMax, 2.4B parameters.

Open weightsMIT971/1044
MiniMax

MiniMax-H3

SIZE33B
85Quality
Video generation · Vision
TextImageDownloads4.8M/mo
VideoLikes6.2K

Video generation model from MiniMax, 33B parameters.

Open weightsMiniMax H3 Community License Agreement959/1044
MiniMax

MiniMax-M2.7-highspeed

CTX205K
Reasoning · Tools
TextInput$0.60/M
TextOutput$2.40/M

Low-latency M2.7 variant for interactive coding plans and agent loops

Open weightsMIT837/1044
MiniMax

MiniMax-M2.7

CTX205K
70Quality
Reasoning · Tools
TextInput$0.30/M
TextOutput$1.20/M

Open MiniMax flagship for coding agents, office automation, and complex environments

Open weightsCustom license836/1044
MiniMax

MiniMax-M2.5-highspeed

CTX205K
Reasoning · Tools
TextInput$0.60/M
TextOutput$2.40/M

High-speed MiniMax model for low-latency coding and agent workflows

Open weightsMIT779/1044
MiniMax

MiniMax-M2.5

CTX205K
74Quality
Reasoning · Tools
TextInput$0.30/M
TextOutput$1.20/M

Prior MiniMax coding model for agent workflows, office edits, and automation

Open weightsModified MIT778/1044
MiniMax

MiniMax-M2.1

CTX205K
60Quality
Reasoning · Tools
TextInput$0.30/M
TextOutput$1.20/M

Earlier MiniMax agent model for practical coding and productivity tasks

Open weightsModified MIT732/1044
Deck0/4
  1. Empty slot
  2. Empty slot
  3. Empty slot
  4. Empty slot